Cambios para capturar la url

Mantengo rutina anterior, ya que ha servido de base para hacer la nueva, que es parecida.
This commit is contained in:
pipcat
2018-04-13 09:40:54 +02:00
committed by GitHub
parent f72a8100af
commit 2ef4234a42

View File

@@ -18,6 +18,58 @@ def test_video_exists(page_url):
def get_video_url(page_url, premium=False, user="", password="", video_password=""):
logger.info("url=" + page_url)
data = httptools.downloadpage(page_url).data
cgi_counter = scrapertools.find_single_match(data, """(?is)src=.(https://www.flashx.bz/counter.cgi.*?[^(?:'|")]+)""")
cgi_counter = cgi_counter.replace("%0A","").replace("%22","")
httptools.downloadpage(cgi_counter, cookies=False)
time.sleep(6)
url_playitnow = "https://www.flashx.bz/dl?playitnow"
fid = scrapertools.find_single_match(data, 'input type="hidden" name="id" value="([^"]*)"')
fname = scrapertools.find_single_match(data, 'input type="hidden" name="fname" value="([^"]*)"')
fhash = scrapertools.find_single_match(data, 'input type="hidden" name="hash" value="([^"]*)"')
headers = {'Content': 'application/x-www-form-urlencoded'}
post_parameters = {
"op": "download1",
"usr_login": "",
"id": fid,
"fname": fname,
"referer": "https://www.flashx.bz/",
"hash": fhash,
"imhuman": "Continue To Video"
}
data = httptools.downloadpage(url_playitnow, urllib.urlencode(post_parameters), headers=headers).data
video_urls = []
media_urls = scrapertools.find_multiple_matches(data, "{src: '([^']+)'.*?,label: '([^']+)'")
subtitle = ""
for media_url, label in media_urls:
if media_url.endswith(".srt") and label == "Spanish":
try:
from core import filetools
data = httptools.downloadpage(media_url)
subtitle = os.path.join(config.get_data_path(), 'sub_flashx.srt')
filetools.write(subtitle, data)
except:
import traceback
logger.info("Error al descargar el subtítulo: " + traceback.format_exc())
for media_url, label in media_urls:
if not media_url.endswith("png") and not media_url.endswith(".srt"):
video_urls.append(["." + media_url.rsplit('.', 1)[1] + " [flashx]", media_url, 0, subtitle])
for video_url in video_urls:
logger.info("%s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url_anterior(page_url, premium=False, user="", password="", video_password=""):
logger.info("url=" + page_url)
pfxfx = ""
data = httptools.downloadpage(page_url, cookies=False).data
data = data.replace("\n","")